Click fraud - Google fights back

by Darren McLaughlin

The charges of click fraud at Google are constant. Google knows this and offered a statement on their official blog. In effect, Google wants us to all know that adequate measures are being taken to fight click fraud. The post was made by Shuman Ghosemajumder, Business Product Manager, Trust and Safety.

He comments of a report by a third party concering Google’s anti-click fraud measures. Highlights of the report include:

“Google has built the following four ‘lines of defense’ for detecting invalid clicks: pre-filtering, online filtering, automated offline detection and manual offline detection, in that order. Google deploys different detection methods in each of these stages: the rule-based and anomaly-based approaches in the pre-filtering and the filtering stages, the combination of all the three approaches in the automated offline detection stage, and the anomaly-based approach in the offline manual inspection stage. This deployment of different methods in different stages gives Google an opportunity to detect invalid clicks using alternative techniques and thus increases their chances of detecting more invalid clicks in one of these stages, preferably proactively in the early stages.” (p. 47)

Obviously, they aren’t planning on going into great detail about the actual methods, but the point is clear. They’ve had a pro-active system in place for some time. What’s been causing even more trepidation against potential advertisers is the appearance of click fraud botnets, which are truly a concern to anyone.

The report is interesting, but it doesn’t cover such obvious potential problems as “social engineering”. People who click the ads themselves, without automation, could go on undetected for years. Click-fraud is the rotting core of the contextual ad game.